Neural Network Optimization

Collaborative Multi-Mode Pruning for Vision-Language Models CVPR 2026 Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation CVPR 2026 Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression CVPR 2026 Dynamic Momentum Recalibration in Online Gradient Learning CVPR 2026 Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry UAI 2026 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks JMLR 2026 How to Set β_1, β_2 in Adam: An Online Learning Perspective ALT 2026 Mapping Networks CVPR 2026 NTK-Guided Implicit Neural Teaching CVPR 2026 Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup–Stable–Decay (Extended Abstract) COLT 2026 Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection JMLR 2026 Reparameterized Complex-valued Neurons Can Efficiently Learn More than Real-valued Neurons via Gradient Descent JMLR 2026 Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability UAI 2026 Revisiting Downsampling in Semantic Segmentation: Fighting Aliasing with Dynamic Gaussian and Gabor Frequency Filters AAAI 2026 Revisiting Layer Normalization for Point Cloud Test Time Adaptation WACV 2026 Revisiting Network Inertia: Dynamic Inertia Inhibition Coupled Multidimensional Periodicity for Infrared and Visible Image Fusion AAAI 2026 The Convergence Behavior of Adam under Heavy-Tailed Noise UAI 2026 TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies CVPR 2026 Understanding, Accelerating, and Improving MeanFlow Training CVPR 2026 Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between WACV 2026 A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training CVPR 2025 Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks AAAI 2025 Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution CVPR 2025 Adaptive Gradient Learning for Spiking Neural Networks by Exploiting Membrane Potential Dynamics IJCAI 2025 Adaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training CVPR 2025